© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15742
    Prev
    Next
    INDEX
    Explanations

    locations followed by type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨è¿Ļç§į
    -0.22
    é£Łåĵģå®īåħ¨
    -0.19
    çļĦä¸Ģ项
    -0.18
    è¿Ļ对
    -0.18
    ä¸Ńåħ³
    -0.18
    è¿Ļç§į
    -0.18
     nét
    -0.18
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.18
     Powered
    -0.18
    _-_
    -0.18
    POSITIVE LOGITS
     hẳn
    0.22
    æ´¥
    0.21
    å¦Ļ
    0.21
    breaker
    0.19
    åį°è±¡æ·±åĪ»
    0.19
    身影
    0.19
    reste
    0.18
    è´¡çĮ®
    0.18
     bulk
    0.18
    ApiController
    0.18
    Activations Density 0.235%

    No Known Activations